MCP cover image
See in Github
2025-03-22

PubMed-MCP-Smithery

1

Github Watches

1

Github Forks

2

Github Stars

PubMed Enhanced Search MCP Server

smithery badge

A Model Content Protocol server that provides enhanced tools to search and retrieve academic papers from PubMed database, with additional features such as MeSH term lookup, publication count statistics, and PICO-based evidence search.

Features

  • Search PubMed by keywords with optional journal filter
  • Support for sorting results by relevance or date (newest/oldest first)
  • Get MeSH (Medical Subject Headings) terms related to a search word
  • Get publication counts for multiple search terms (useful for comparing prevalence)
  • Retrieve detailed paper information including abstract, DOI, authors, and keywords
  • Perform structured PICO-based searches with support for synonyms and combination queries

Installing

Prerequisites

  • Python 3.6+
  • pip

Installation

  1. Clone this repository:

    git clone https://github.com/leescot/pubmed-mcp-smithery
    cd pubmed-mcp-smithery
    
  2. Install dependencies:

    pip install fastmcp requests
    

Usage

Running locally

Start the server:

python pubmed_enhanced_mcp_server.py

For development mode with auto-reloading:

mcp dev pubmed_enhanced_mcp_server.py

Adding to Claude Desktop

Edit your Claude Desktop configuration file (CLAUDE_DIRECTORY/claude_desktop_config.json) to add the server:

"pubmed-enhanced": {
    "command": "python",
    "args": [
        "/path/pubmed-mcp-smithery/pubmed_enhanced_mcp_server.py"
    ]
}

MCP Functions

The server provides these main functions:

  1. search_pubmed - Search PubMed for articles matching keywords with optional journal filtering

    # Example
    results = await search_pubmed(
        keywords=["diabetes", "insulin resistance"],
        journal="Nature Medicine",
        num_results=5,
        sort_by="date_desc"
    )
    
  2. get_mesh_terms - Look up MeSH terms related to a medical concept

    # Example
    mesh_terms = await get_mesh_terms("diabetes")
    
  3. get_pubmed_count - Get the count of publications for multiple search terms

    # Example
    counts = await get_pubmed_count(["diabetes", "obesity", "hypertension"])
    
  4. format_paper_details - Get detailed information about specific papers by PMID

    # Example
    paper_details = await format_paper_details(["12345678", "87654321"])
    
  5. pico_search - Perform structured PICO (Population, Intervention, Comparison, Outcome) searches with synonyms

    # Example
    pico_results = await pico_search(
        p_terms=["diabetes", "type 2 diabetes", "T2DM"],
        i_terms=["metformin", "glucophage"],
        c_terms=["sulfonylurea", "glipizide"],
        o_terms=["HbA1c reduction", "glycemic control"]
    )
    

PICO Search Functionality

The PICO search tool helps researchers conduct evidence-based literature searches by:

  1. Allowing multiple synonym terms for each PICO element
  2. Combining terms within each element using OR operators
  3. Performing AND combinations between elements (P AND I, P AND I AND C, etc.)
  4. Returning both search queries and publication counts for each combination

This approach helps refine research questions and identify the most relevant literature.

Rate Limiting

The server implements automatic retry mechanism with backoff delays to handle potential rate limiting by NCBI's E-utilities service.

License

This project is licensed under the BSD 3-Clause License - see the LICENSE file for details.

相关推荐

  • NiKole Maxwell
  • I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Yusuf Emre Yeşilyurt
  • I find academic articles and books for research and literature reviews.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Carlos Ferrin
  • Encuentra películas y series en plataformas de streaming.

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • lumpenspace
  • Take an adjectivised noun, and create images making it progressively more adjective!

  • apappascs
  • Descubra la colección más completa y actualizada de servidores MCP en el mercado. Este repositorio sirve como un centro centralizado, que ofrece un extenso catálogo de servidores MCP de código abierto y propietarios, completos con características, enlaces de documentación y colaboradores.

  • ShrimpingIt
  • Manipulación basada en Micrypthon I2C del expansor GPIO de la serie MCP, derivada de AdaFruit_MCP230xx

  • huahuayu
  • Una puerta de enlace de API unificada para integrar múltiples API de explorador de blockchain similar a Esterscan con soporte de protocolo de contexto modelo (MCP) para asistentes de IA.

  • modelcontextprotocol
  • Servidores de protocolo de contexto modelo

  • Mintplex-Labs
  • La aplicación AI de escritorio todo en uno y Docker con trapo incorporado, agentes de IA, creador de agentes sin código, compatibilidad de MCP y más.

    Reviews

    4 (1)
    Avatar
    user_bN0wo9pC
    2025-04-16

    I've been using pubmed-mcp-smithery for a while, and it is an incredible tool for managing PubMed articles. Developed by leescot, it's user-friendly and highly efficient in sorting and accessing relevant research papers. Highly recommend it for anyone involved in academic research or needing quick access to PubMed data. Check it out at: https://github.com/leescot/pubmed-mcp-smithery.